Anomaly Detection

Detect signal anomalies using AI models, including deep learning networks

Extract sparse time-frequency features to detect anomalies in electromagnetic, acoustic, and vibration data.

Functions

deepSignalAnomalyDetector Create signal anomaly detector (Since R2023a)

`audioDatastore`	Datastore for collection of audio files
`arrayDatastore`	Datastore for in-memory data
`signalDatastore`	Datastore for collection of signals
`imageDatastore`	Datastore for image data
`waveletScattering`	Wavelet time scattering
`signalTimeFeatureExtractor`	Streamline signal time feature extraction (Since R2021a)
`signalFrequencyFeatureExtractor`	Streamline signal frequency feature extraction (Since R2021b)
`signalTimeFrequencyFeatureExtractor`	Streamline signal time-frequency feature extraction (Since R2024a)
`stftLayer`	Short-time Fourier transform layer (Since R2021b)
`istftLayer`	Inverse short-time Fourier transform layer (Since R2024a)
`cwtLayer`	Continuous wavelet transform layer (Since R2022b)
`icwtLayer`	Inverse continuous wavelet transform layer (Since R2024b)
`modwtLayer`	Maximal overlap discrete wavelet transform layer (Since R2022b)

Detect anomalies in acoustic data using wavelet scattering and the deepSignalAnomalyDetector object.

Use autoencoders to detect abnormal points or segments in time-series data.

Use a long short-term memory autoencoder to detect anomalies in data from an industrial machine.

Use wavelet and deep learning techniques to detect and localize transverse pavement cracks.

(Deep Learning Toolbox)

Learn how to develop an alert system for predictive maintenance using wavelet scattering and deep learning.

(Deep Learning Toolbox)

Classify faults in acoustic recordings of air compressors using a wavelet scattering network paired with a recurrent neural network.

(Deep Learning Toolbox)